© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 222798
    Prev
    Next
    INDEX
    Explanations

    discounts on site

    np_acts-logits-general · gemini-2.5-flash-lite

    handles context following specific actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     территории
    0.55
    ène
    0.51
     требуется
    0.50
    డ్‌
    0.49
    ニング
    0.48
     территория
    0.47
    ō
    0.47
    ெட்
    0.47
     প্রতিনিধিদের
    0.46
    咧
    0.46
    POSITIVE LOGITS
    al
    0.59
     ist
    0.53
    السلام
    0.52
     r
    0.48
    Optimize
    0.47
     yoga
    0.46
    cdot
    0.46
     spin
    0.46
     moderation
    0.46
     s
    0.44
    Activations Density 0.000%

    No Known Activations